Method and apparatus for performing communication by using ai / ml

Abstract

The present embodiments provide a method by which a terminal performs communication by using artificial intelligence and machine learning (AI / ML), the method comprising the steps of: receiving, from a base station, a group ID associated with a dataset provided for training an AI / ML model; determining whether the received group ID matches a group ID for the AI / ML model stored in the terminal; and when the received group ID does not match the group ID for the AI / ML model stored in the terminal, performing data collection on the basis of at least one associated ID corresponding to the received group ID.

Description

Method and apparatus for performing communication using artificial intelligence and machine learning

[0001] The embodiments propose a method and apparatus for performing communication using artificial intelligence and machine learning in a next-generation wireless access network (in this disclosure, "5G", "NR [New Radio]", "5G-Advanced", "6G" or subsequent 3GPP wireless access networks).

[0002] As next-generation wireless communication technology evolves beyond 5G to 6G, it aims to achieve faster data transmission speeds and ultra-low latency compared to 5G in ultra-high frequency bands such as the terahertz (THz) band. Accordingly, technology is advancing in the direction of incorporating artificial intelligence (AI) and machine learning (ML) technologies from the design stage of communication systems. As a result, wireless communication systems are establishing a technical foundation to support new services and applications in an ultra-high performance, ultra-low latency, and ultra-connected environment.

[0003] In particular, AI / ML technologies are being introduced in wireless communication networks to optimize network operations and ensure real-time quality. By performing various roles such as situational awareness through big data analysis, adaptive utilization of network resources and data, and intelligent, data-driven system optimization, AI / ML can enable efficient resource management and service quality improvement in complex wireless environments, over which existing methods had limitations.

[0004] As part of this aspect, a specific design is required to enable wireless communication using AI / ML models.

[0005] Embodiments of the present disclosure may provide a method and apparatus for performing communication using artificial intelligence and machine learning in a next-generation wireless access network.

[0006] In one aspect, the present embodiments may provide a method for a terminal (user equipment; UE) to perform communication using artificial intelligence and machine learning (AI / ML), comprising the steps of: receiving a group ID associated with a dataset provided for training an AI / ML model from a base station; determining whether the received group ID matches a group ID for an AI / ML model stored in the terminal; and, if the received group ID does not match a group ID for an AI / ML model stored in the terminal, performing data collection based on at least one associated ID corresponding to the received group ID.

[0007] In another aspect, the present embodiments may provide a method for a base station to perform communication using artificial intelligence and machine learning (AI / ML), comprising the steps of: transmitting a group ID associated with a dataset provided for training an AI / ML model to a terminal; when a request for a dataset provided for training an AI / ML model is received from the terminal, transmitting data collection configuration information corresponding to at least one associated ID to the terminal; and transmitting data for data collection of the terminal based on the data collection configuration information.

[0008] In another aspect, the embodiments may provide a terminal (user equipment; UE) that performs communication using artificial intelligence and machine learning (AI / ML), comprising a transmitter, a receiver, and a control unit that controls the operation of the transmitter and the receiver, wherein the control unit receives a group ID associated with a dataset provided for training an AI / ML model from a base station, determines whether the received group ID matches a group ID for an AI / ML model stored in the terminal, and if the received group ID does not match a group ID for an AI / ML model stored in the terminal, the terminal performs data collection based on at least one associated ID corresponding to the received group ID.

[0009] In another aspect, the embodiments may provide a base station that performs communication using artificial intelligence and machine learning, comprising a transmitter, a receiver, and a control unit that controls the operation of the transmitter and the receiver, wherein the control unit transmits a group ID associated with a dataset provided for training an AI / ML model to a terminal, and when a request for a dataset provided for training an AI / ML model is received from the terminal, transmits data collection configuration information corresponding to at least one associated ID to the terminal, and transmits data for data collection of the terminal based on the data collection configuration information.

[0010] According to the embodiments, a method and apparatus for performing communication using artificial intelligence and machine learning in a next-generation wireless access network can be provided.

[0011] In addition, according to the embodiments, by determining whether model training is required at the base station through the reception of a group ID for the base station, a trained model is obtained before performing model inference, thereby enabling model inference to be performed in a timely manner as needed.

[0012] In addition, according to the embodiments, the total signaling overhead can be reduced by transmitting only the group ID or, if necessary, signaling only the associated ID within the group ID.

[0013] FIG. 1 is a diagram briefly illustrating the structure of an NR wireless communication system to which the present embodiment can be applied.

[0014] FIG. 2 is a drawing illustrating the frame structure in an NR system to which the present embodiment can be applied.

[0015] FIG. 3 is a diagram illustrating a resource grid supported by wireless access technology to which the present embodiment can be applied.

[0016] FIG. 4 is a diagram illustrating the bandwidth part supported by the wireless access technology to which the present embodiment can be applied.

[0017] FIG. 5 is a diagram illustrating an exemplary synchronization signal block in a wireless access technology to which the present embodiment can be applied.

[0018] FIG. 6 is a diagram illustrating a random access procedure in a wireless access technology to which the present embodiment can be applied.

[0019] Figure 7 is a diagram for explaining CORESET.

[0020] FIG. 8 is a diagram illustrating a procedure in which a terminal according to one embodiment performs communication using artificial intelligence and machine learning.

[0021] FIG. 9 is a diagram illustrating a procedure in which a base station according to one embodiment performs communication using artificial intelligence and machine learning.

[0022] FIG. 10 is a diagram illustrating the operation when base stations with the same associated ID are grouped according to one embodiment.

[0023] FIG. 11 is a diagram for explaining the operation when base stations are grouped according to a predetermined standard according to one embodiment.

[0024] FIG. 12 is a diagram showing the configuration of a terminal according to another embodiment.

[0025] FIG. 13 is a diagram showing the configuration of a base station according to another embodiment.

[0026] Hereinafter, some embodiments of the present disclosure will be described in detail with reference to the exemplary drawings. In assigning reference numerals to the components of each drawing, the same components may have the same reference numeral as much as possible, even if they are shown in different drawings. Furthermore, in describing the embodiments, if it is determined that a detailed description of related known components or functions may obscure the essence of the technical concept, such detailed description may be omitted. Where terms such as "comprising," "having," or "consisting of" are used in this specification, other parts may be added unless "only" is used. Where a component is expressed in the singular, it may include a plural unless otherwise specified.

[0027] Additionally, terms such as first, second, A, B, (a), (b), etc., may be used to describe the components of the present disclosure. These terms are used merely to distinguish the components from other components, and the nature, order, sequence, or number of the components are not limited by such terms.

[0028] In describing the positional relationship of components, where it is stated that two or more components are "connected," "combined," or "joined," it should be understood that while the two or more components may be directly "connected," "combined," or "joined," they may also be "connected," "combined," or "joined" with other components "intervened." Here, the other components may be included in one or more of the two or more components that are "connected," "combined," or "joined" with one another.

[0029] In describing the temporal flow relationship regarding components, methods of operation, or methods of production, for example, when the temporal or sequential relationship is described using "after," "following," "next," or "before," it may include cases where the relationship is not continuous unless "immediately" or "directly" is used.

[0030] Meanwhile, where numerical values ​​or corresponding information regarding a component (e.g., levels, etc.) are mentioned, even without separate explicit notation, the numerical values ​​or corresponding information may be interpreted as including a range of error that may occur due to various factors (e.g., process factors, internal or external shocks, noise, etc.).

[0031] A wireless communication system in this specification refers to a system for providing various communication services, such as voice and data packets, using wireless resources, and may include a terminal, a base station, or a core network.

[0032] The embodiments disclosed below may be applied to wireless communication systems using various wireless access technologies. For example, the embodiments may be applied to various wireless access technologies such as CDMA (code division multiple access), FDMA (frequency division multiple access), TDMA (time division multiple access), OFDMA (orthogonal frequency division multiple access), SC-FDMA (single carrier frequency division multiple access), or NOMA (non-orthogonal multiple access). Furthermore, wireless access technology may refer not only to specific access technologies but also to communication technologies for each generation established by various telecommunication organizations such as 3GPP, 3GPP2, WiFi, Bluetooth, IEEE, and ITU. For example, CDMA may be implemented as a wireless technology such as UTRA (universal terrestrial radio access) or CDMA2000. TDMA may be implemented as a wireless technology such as GSM (global system for mobile communications), GPRS (general packet radio service), or EDGE (enhanced datarates for GSM evolution). OFDMA can be implemented using wireless technologies such as IEEE (Institute of Electrical and Electronic Engineers) 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802-20, and E-UTRA (evolved UTRA). IEEE 802.16m is an evolution of IEEE 802.16e and provides backward compatibility with systems based on IEEE 802.16e.UTRA is part of UMTS (universal mobile telecommunications system). 3GPP (3rd generation partnership project) LTE (long term evolution) is part of E-UMTS (evolved UMTS) that uses E-UTRA (evolved-UMTS terrestrial radio access), employing OFDMA in the downlink and SC-FDMA in the uplink. As such, these embodiments can be applied to currently disclosed or commercialized radio access technologies, and can also be applied to radio access technologies currently under development or to be developed in the future.

[0033] Meanwhile, the term "terminal" in this specification is a comprehensive concept meaning a device including a wireless communication module that communicates with a base station in a wireless communication system. It should be interpreted as a concept that includes not only User Equipment (UE) in WCDMA, LTE, NR, HSPA, and IMT-2020 (5G or New Radio), but also Mobile Station (MS), User Terminal (UT), Subscriber Station (SS), and wireless device in GSM. Furthermore, depending on the usage type, the terminal may be a user portable device such as a smartphone, or in a V2X communication system, it may refer to a vehicle or a device including a wireless communication module inside a vehicle. Additionally, in the case of a Machine Type Communication (MMC) system, it may refer to an MTC terminal, M2M terminal, URLLC terminal, etc., equipped with a communication module to perform machine type communication.

[0034] In this specification, "base station" or "cell" refers to an end that communicates with a terminal in terms of a network, and encompasses various coverage areas such as Node-B, eNB (evolved Node-B), gNB (gNode-B), LPN (Low Power Node), Sector, Site, various types of antennas, BTS (Base Transceiver System), Access Point, Point (e.g., Transmitter Point, Receiver Point, Transceiver Point), Relay Node, Mega Cell, Macro Cell, Micro Cell, Pico Cell, Femto Cell, RRH (Remote Radio Head), RU (Radio Unit), and Small Cell. Additionally, "cell" may include a Bandwidth Part (BWP) in the frequency domain. For example, a serving cell may refer to the Activation BWP of a terminal.

[0035] Since there is a base station controlling one or more of the various cells listed above, the term "base station" can be interpreted in two senses. 1) It may refer to the device itself that provides a mega cell, macro cell, micro cell, pico cell, femto cell, or small cell in relation to a wireless area, or 2) it may refer to the wireless area itself. In 1), all devices that provide a specific wireless area are controlled by the same entity or interact to configure the wireless area collaboratively are referred to as base stations. Depending on the configuration method of the wireless area, a point, a transmitting / receiving point, a transmitting point, a receiving point, etc., are examples of a base station. In 2), the wireless area itself that receives or transmits a signal from the perspective of a user terminal or from the perspective of a neighboring base station may also be referred to as a base station.

[0036] In this specification, "Cell" may refer to a component carrier having coverage of a signal transmitted from a transmitting / receiving point or coverage of a signal transmitted from a transmitting / receiving point (transmission point or transmission / reception point), or the transmitting / receiving point itself.

[0037] Uplink (UL, or Uplink) refers to the method of transmitting and receiving data from a terminal to a base station, and Downlink (DL, or Downlink) refers to the method of transmitting and receiving data from a base station to a terminal. Downlink may refer to communication or a communication path from multiple transmission and reception points to a terminal, and uplink may refer to communication or a communication path from a terminal to multiple transmission and reception points. In this case, in the downlink, the transmitter may be part of the multiple transmission and reception points, and the receiver may be part of the terminal. Additionally, in the uplink, the transmitter may be part of the terminal, and the receiver may be part of the multiple transmission and reception points.

[0038] The uplink and downlink transmit and receive control information through control channels such as PDCCH (Physical Downlink Control Channel) and PUCCH (Physical Uplink Control Channel), and transmit and receive data by configuring data channels such as PDSCH (Physical Downlink Shared Channel) and PUSCH (Physical Uplink Shared Channel). In the following description, the situation in which signals are transmitted and received through channels such as PUCCH, PUSCH, PDCCH, and PDSCH is also referred to as "transmitting and receiving PUCCH, PUSCH, PDCCH, and PDSCH."

[0039] To clarify the explanation, the technical concept described below is primarily based on 3GPP LTE / LTE-A / NR (New RAT) communication systems, but the technical features are not limited to said communication systems.

[0040] Following research on 4G (4th-Generation) communication technology, 3GPP develops 5G (5th-Generation) communication technology to meet the requirements of the ITU-R for next-generation radio access technology. Specifically, 3GPP develops LTE-A pro, which enhances LTE-Advanced technology to meet ITU-R requirements, and NR, a new communication technology distinct from 4G communication technology, as 5G communication technologies. Since both LTE-A pro and NR refer to 5G communication technology, the following description of 5G communication technology will focus on NR unless a specific technology is being identified.

[0041] The operational scenarios in NR define various operation scenarios by adding considerations for satellites, automobiles, and new verticals to the existing 4G LTE scenarios, and in terms of service, they support eMBB (Enhanced Mobile Broadband) scenarios, mMTC (Massive Machine Communication) scenarios which require low data rates and asynchronous access while having high terminal density and being deployed over a wide range, and URLLC (Ultra Reliability and Low Latency) scenarios which require high responsiveness and reliability and can support high-speed mobility.

[0042] To satisfy these scenarios, NR introduces a wireless communication system equipped with new waveform and frame structure technologies, low latency technology, mmWave support technology, and forward compatibility technology. In particular, the NR system presents various technical changes in terms of flexibility to provide forward compatibility. The main technical features of NR are explained below with reference to the drawings.

[0043]

[0044] <NR 시스템 일반>

[0045] FIG. 1 is a simplified diagram illustrating the structure of an NR system to which the present embodiment can be applied.

[0046] Referring to FIG. 1, the NR system is divided into a 5G Core Network (5GC) and an NR-RAN part. The NG-RAN consists of gNBs and ng-eNBs that provide control plane (RRC) protocol endpoints for the user plane (SDAP / PDCP / RLC / MAC / PHY) and User Equipment (UE). gNBs are interconnected with each other, or gNBs and ng-eNBs are interconnected via Xn interfaces. Each gNB and ng-eNB is connected to the 5GC via an NG interface. The 5GC may be configured to include an Access and Mobility Management Function (AMF), which is responsible for control plane functions such as terminal access and mobility control, and a User Plane Function (UPF), which is responsible for control functions for user data. The NR system includes support for both frequency bands below 6 GHz (FR1, Frequency Range 1) and frequency bands above 6 GHz (FR2, Frequency Range 2).

[0047] gNB refers to a base station that provides NR user plane and control plane protocol terminations to a terminal, and ng-eNB refers to a base station that provides E-UTRA user plane and control plane protocol terminations to a terminal. The base station described in this specification should be understood as encompassing both gNB and ng-eNB, and may also be used to refer to gNB or ng-eNB separately as necessary.

[0048] <NR 웨이브 폼, 뉴머롤러지 및 프레임 구조>

[0049]

[0050] In NR, CP-OFDM waveforms using a cyclic prefix are used for downlink transmission, and CP-OFDM or DFT-s-OFDM are used for uplink transmission. OFDM technology is easy to combine with MIMO (Multiple Input Multiple Output) and has the advantage of allowing the use of low-complexity receivers along with high frequency efficiency.

[0051] Meanwhile, in NR, since the requirements for data rate, latency, coverage, etc. differ for each of the three scenarios mentioned above, it is necessary to efficiently satisfy the requirements for each scenario through the frequency bands that constitute an arbitrary NR system. To this end, a technology has been proposed to efficiently multiplex wireless resources based on multiple different numerologies.

[0052] Specifically, the NR transmission numerator is determined based on sub-carrier spacing and CP (Cyclic prefix), and as shown in Table 1 below, the μ value is used as an exponential value of 2 based on 15 kHz and changes exponentially.

[0053] μ서브캐리어 간격Cyclic prefixSupported for dataSupported for synch015NormalYesYes130NormalYesYes260Normal, ExtendedYesNo3120NormalYesYes4240NormalNoYes

[0054] As shown in Table 1 above, the numerators of NR can be classified into five types based on the subcarrier spacing. This differs from LTE, one of the 4G communication technologies, where the subcarrier spacing is fixed at 15 kHz. Specifically, the subcarrier spacings used for data transmission in NR are 15, 30, 60, and 120 kHz, while the subcarrier spacings used for synchronization signal transmission are 15, 30, 12, and 240 kHz. Additionally, extended CP applies only to the 60 kHz subcarrier spacing. Meanwhile, the frame structure in NR defines a frame with a length of 10ms, composed of 10 subframes of equal length of 1ms. A single frame can be divided into 5ms half-frames, and each half-frame contains 5 subframes. In the case of a 15 kHz subcarrier interval, one subframe consists of one slot, and each slot consists of 14 OFDM symbols. FIG. 2 is a diagram illustrating the frame structure in an NR system to which the present embodiment can be applied. Referring to FIG. 2, in the case of a normal CP, the slot is fixedly composed of 14 OFDM symbols, but the length of the slot in the time domain may vary depending on the subcarrier interval. For example, in the case of a numeral with a 15 kHz subcarrier interval, the slot is composed of a length of 1 ms, which is the same length as the subframe. In contrast, in the case of a numeral with a 30 kHz subcarrier interval, the slot is composed of 14 OFDM symbols, but two slots may be included in one subframe with a length of 0.5 ms. That is, the subframe and the frame are defined with a fixed time length, while the slot is defined by the number of symbols, and the time length may vary depending on the subcarrier interval.Meanwhile, NR defines the basic unit of scheduling as a slot and introduced mini-slots (or sub-slots or non-slot based schedules) to reduce transmission delay in the wireless section. Using a wide subcarrier spacing reduces transmission delay in the wireless section because the length of a single slot becomes inversely shorter. Mini-slots (or sub-slots) are designed for efficient support of URLLC scenarios and allow scheduling in units of 2, 4, or 7 symbols.

[0055] Furthermore, unlike LTE, NR defines uplink and downlink resource allocation at the symbol level within a single slot. To reduce HARQ latency, a slot structure was defined that allows HARQ ACK / NACK to be transmitted directly within the transmission slot; this slot structure is described as a self-contained structure.

[0056] NR is designed to support a total of 256 slot formats, of which 62 are used in 3GPP Rel-15. Additionally, it supports common frame structures that form FDD or TDD frames through various slot combinations. For example, it supports slot structures where all slot symbols are set to downlink, slot structures where all symbols are set to uplink, and slot structures where downlink and uplink symbols are combined. Furthermore, NR supports data transmission being distributed and scheduled across one or more slots. Therefore, base stations can use a Slot Format Indicator (SFI) to inform a terminal whether a slot is a downlink slot, an uplink slot, or a flexible slot. Base stations can indicate the slot format by using the SFI to indicate an index of a table configured via UE-specific RRC signaling, or they can indicate it dynamically via Downlink Control Information (DCI) or statically or semi-statically via RRC.

[0057] <NR 물리 자원 >

[0058] Regarding physical resources in NR, antenna ports, resource grids, resource elements, resource blocks, and bandwidth parts are considered.

[0059] An antenna port is defined such that the channel carrying a symbol on the antenna port can be inferred from the channel carrying another symbol on the same antenna port. If the large-scale property of the channel carrying a symbol on one antenna port can be inferred from the channel carrying a symbol on another antenna port, the two antenna ports can be said to be in a QC / QCL (quasi co-located or quasi co-location) relationship. Here, the large-scale property includes one or more of delay spread, Doppler spread, frequency shift, average received power, and received timing.

[0060] FIG. 3 is a diagram illustrating a resource grid supported by wireless access technology to which the present embodiment can be applied.

[0061] Referring to FIG. 3, a resource grid may exist for each numerator because NR supports multiple numerators on the same carrier. Additionally, a resource grid may exist depending on the antenna port, subcarrier spacing, and transmission direction.

[0062] A resource block consists of 12 subcarriers and is defined only in the frequency domain. Additionally, a resource element consists of one OFDM symbol and one subcarrier. Therefore, as shown in Fig. 3, the size of a single resource block can vary depending on the subcarrier spacing. Furthermore, NR defines "Point A," which serves as a common reference point for the resource block grid, as well as common resource blocks, virtual resource blocks, etc.

[0063] FIG. 4 is a diagram illustrating the bandwidth part supported by the wireless access technology to which the present embodiment can be applied.

[0064] In NR, unlike LTE where the carrier bandwidth is fixed at 20 MHz, the maximum carrier bandwidth is set from 50 MHz to 400 MHz depending on the subcarrier interval. Therefore, it is not assumed that all terminals use this entire carrier bandwidth. Accordingly, in NR, as shown in Fig. 4, a Bandwidth Part (BWP) can be designated within the carrier bandwidth for the terminal to use. Additionally, a Bandwidth Part is associated with a single numerator and consists of a subset of a continuous common resource block, and can be dynamically activated over time. Up to four Bandwidth Parts are configured for the uplink and downlink respectively, and data is transmitted and received using the Bandwidth Part activated at a given time.

[0065] In the case of paired spectrum, the uplink and downlink bandwidth parts are set independently, whereas in the case of unpaired spectrum, the downlink and uplink bandwidth parts are paired to share a center frequency in order to prevent unnecessary frequency re-tuning between downlink and uplink operations.

[0066] <NR 초기 접속>

[0067] In NR, the terminal performs cell search and random access procedures to connect to the base station and perform communication.

[0068] Cell search is a procedure in which a terminal uses a Synchronization Signal Block (SSB) transmitted by a base station to synchronize with the corresponding base station's cell, obtain a physical layer cell ID, and acquire system information.

[0069] FIG. 5 is a diagram illustrating an exemplary synchronization signal block in a wireless access technology to which the present embodiment can be applied.

[0070] Referring to FIG. 5, the SSB consists of a PSS (primary synchronization signal) and an SSS (secondary synchronization signal) each occupying 1 symbol and 127 subcarriers, and a PBCH spanning 3 OFDM symbols and 240 subcarriers.

[0071] The terminal monitors the SSB in the time and frequency domains and receives the SSB.

[0072] SSBs can be transmitted up to 64 times within 5ms. Multiple SSBs are transmitted via different transmission beams within the 5ms timeframe, and the terminal performs detection by assuming that an SSB is transmitted every 20ms based on a specific beam used for transmission. The number of beams available for SSB transmission within the 5ms timeframe can increase as the frequency band increases. For example, up to 4 SSB beams can be transmitted at 3GHz or lower, up to 8 beams in the frequency band from 3GHz to 6GHz, and up to 64 different beams can be used to transmit SSBs in the frequency band above 6GHz.

[0073] Two SSBs are included in a single slot, and the starting symbol and number of repetitions within the slot are determined according to the subcarrier interval as follows.

[0074] Meanwhile, unlike the SS of conventional LTE, the SSB is not transmitted at the center frequency of the carrier bandwidth. That is, the SSB can be transmitted even at locations other than the center of the system band, and multiple SSBs can be transmitted across the frequency domain when broadband operation is supported. Accordingly, the terminal monitors the SSB using a synchronization raster, which is a candidate frequency location for monitoring the SSB. The carrier raster, which is information on the center frequency location of the channel for initial connection, and the synchronization raster were newly defined in NR, and the synchronization raster is set with a wider frequency interval compared to the carrier raster, thereby supporting fast SSB search by the terminal.

[0075] The terminal can obtain the MIB through the PBCH of the SSB. The Master Information Block (MIB) contains minimum information for the terminal to receive the Remaining Minimum System Information (RMSI) broadcast by the network. Additionally, the PBCH may include information regarding the location of the first DM-RS symbol in the time domain, information for the terminal to monitor SIB1 (e.g., SIB1 numeral information, information related to SIB1 CORESET, search space information, PDCCH related parameter information, etc.), and offset information between the Common Resource Block and the SSB (the absolute location of the SSB within the carrier is transmitted via SIB1). Here, the SIB1 numeral information is applied identically to some messages used in the random access procedure for the terminal to connect to the base station after completing the cell search procedure. For example, the SIB1 numeral information may be applied to at least one of messages 1 to 4 for the random access procedure.

[0076] The aforementioned RMSI may refer to SIB1 (System Information Block 1), and SIB1 is broadcast periodically (e.g., 160ms) from the cell. SIB1 contains information necessary for the terminal to perform the initial random access procedure and is transmitted periodically via PDSCH. To receive SIB1, the terminal must receive the numerology information used for transmitting SIB1 and the CORESET (Control Resource Set) information used for scheduling SIB1 via PBCH. The terminal checks the scheduling information for SIB1 using SI-RNTI within the CORESET and obtains SIB1 on the PDSCH according to the scheduling information. The remaining SIBs, excluding SIB1, may be transmitted periodically or upon the terminal's request.

[0077] FIG. 6 is a diagram illustrating a random access procedure in a wireless access technology to which the present embodiment can be applied.

[0078] Referring to FIG. 6, when cell search is completed, the terminal transmits a random access preamble for random access to the base station. The random access preamble is transmitted via PRACH. Specifically, the random access preamble is transmitted to the base station via PRACH, which consists of a series of radio resources in specific slots that are repeated periodically. Generally, when the terminal initially connects to a cell, a contention-based random access procedure is performed, and when performing random access for Beam Failure Recovery (BFR), a non-contention-based random access procedure is performed.

[0079] The terminal receives a random access response for the transmitted random access preamble. The random access response may include a random access preamble identifier (ID), an UL Grant (uplink radio resource), a temporary C-RNTI (Temporary Cell - Radio Network Temporary Identifier), and a TAC (Time Alignment Command). Since a single random access response may contain random access response information for one or more terminals, the random access preamble identifier may be included to indicate which terminal the included UL Grant, temporary C-RNTI, and TAC are valid for. The random access preamble identifier may be an identifier for the random access preamble received by the base station. The TAC may be included as information for the terminal to coordinate uplink synchronization. The random access response may be indicated by the random access identifier on the PDCCH, namely the RA-RNTI (Random Access - Radio Network Temporary Identifier).

[0080] A terminal that receives a valid random access response processes the information contained in the random access response and performs a transmission scheduled to the base station. For example, the terminal applies a TAC and stores a temporary C-RNTI. Additionally, using a UL Grant, it transmits data stored in the terminal's buffer or newly generated data to the base station. In this case, information that can identify the terminal must be included.

[0081] Finally, the terminal receives a downlink message to resolve competition.

[0082] <NR CORESET>

[0083] The downlink control channel in NR is transmitted in a CORESET (Control Resource Set) with a length of 1 to 3 symbols, and transmits uplink / downlink scheduling information, SFI (Slot format Index), TPC (Transmit Power Control) information, etc.

[0084] In this way, NR introduced the concept of CORESET to ensure system flexibility. CORESET (Control Resource Set) refers to time-frequency resources for downlink control signals. A terminal can decode control channel candidates by using one or more search spaces from the CORESET time-frequency resources. Quasi CoLocation (QCL) assumptions were established for each CORESET, and these are used to indicate characteristics regarding the analog beam direction in addition to the characteristics assumed by conventional QCL, such as delay spread, Doppler spread, Doppler shift, and mean delay.

[0085] Figure 7 is a diagram for explaining CORESET.

[0086] Referring to FIG. 7, CORESET can exist in various forms within a single slot and within the carrier bandwidth, and in the time domain, CORESET can be composed of up to 3 OFDM symbols. Additionally, CORESET is defined as a multiple of 6 resource blocks up to the carrier bandwidth in the frequency domain.

[0087] The first CORESET is specified via the MIB as part of the initial bandwidth part configuration to enable the reception of additional configuration and system information from the network. After establishing a connection with the base station, the terminal can be configured by receiving one or more CORESET information via RRC signaling.

[0088] In this specification, frequencies, frames, subframes, resources, resource blocks, regions, bands, subbands, control channels, data channels, synchronization signals, various reference signals, various signals, or various messages related to NR (New Radio) may be interpreted in the sense used in the past or present, or in various senses used in the future.

[0089] Wider bandwidth operations

[0090] In the case of existing LTE systems, scalable bandwidth operation was supported for any LTC Component Carrier (CC). That is, depending on the frequency deployment scenario, any LTE operator could configure a bandwidth ranging from a minimum of 1.4 MHz to a maximum of 20 MHz when configuring a single LTE CC, and normal LTE terminals supported a transmit / receive capability of 20 MHz bandwidth for a single LTE CC.

[0091] However, in the case of NR, the design is made to enable support for NR terminals with different transmit / receive bandwidth capabilities through a single wideband NR CC. Accordingly, it is required to configure one or more bandwidth parts (BWPs) consisting of subdivided bandwidths for any NR CC, and to support flexible wider bandwidth operation through different bandwidth part configurations and activations for each terminal.

[0092] Specifically, in NR, one or more bandwidth parts can be configured through a single serving cell configured from the perspective of a terminal, and the terminal is defined to activate one downlink bandwidth part (DL bandwidth part) and one uplink bandwidth part (UL bandwidth part) in the serving cell to use for uplink / downlink data transmission and reception. In addition, for terminals where multiple serving cells are configured, i.e., terminals to which CA is applied, it is defined to activate one downlink bandwidth part and / or uplink bandwidth part for each serving cell to use the wireless resources of the serving cell for uplink / downlink data transmission and reception.

[0093] Specifically, an initial bandwidth part for the initial access procedure of a terminal is defined in any serving cell, and one or more terminal-specific (UE-specific) bandwidth parts are configured for each terminal through dedicated RRC signaling, and a default bandwidth part for a fallback operation can also be defined for each terminal.

[0094] However, depending on the capability and bandwidth part(s) configuration of the terminal in any serving cell, it may be defined to simultaneously activate and use multiple downlink and / or uplink bandwidth parts, but in NR rel-15, it is defined to activate and use only one downlink bandwidth part (DL bandwidth part) and one uplink bandwidth part (UL bandwidth part) at any time in any terminal.

[0095]

[0096] The present disclosure relates to a method for ensuring consistency between NW or UE conditions between training and inference in a system for performing wireless communication using an AI / ML model by a terminal, when a model trained based on data collection provided by a network (NW) is applied to inference. In particular, the present invention proposes a method for notifying the terminal of information regarding one or more cells to which the same network-side additional condition corresponding to an associated ID is applied. Upon receiving this information, the terminal performs training on the relevant model based on group information.

[0097] Regarding AI / ML-applied wireless communication, terms can be defined as follows.

[0098] Data collection refers to the process by which network nodes, managed entities, or UEs collect data for the purpose of training AI / ML models, data analysis, and inference.

[0099] An AI / ML model (hereinafter also referred to as a 'model') refers to a data-driven algorithm that applies AI / ML technology to generate a series of outputs based on a series of inputs. AI / ML model training refers to the process of training an AI / ML model in a data-driven manner by learning input / output relationships, and obtaining the trained AI / ML model for inference. AI / ML model inference refers to the process of generating a series of outputs based on a series of inputs using the trained AI / ML model. AI / ML model validation refers to a sub-process of training that evaluates the quality of an AI / ML model using a dataset different from the one used for training. AI / ML model testing refers to a sub-process of training used to evaluate the performance of the final AI / ML model using a dataset different from those used for training and validation. Unlike AI / ML model validation, testing does not assume subsequent tuning of the model.

[0100] A UE-side (AI / ML) model refers to an AI / ML model where inference is performed entirely within the UE. A Network-side (AI / ML) model refers to an AI / ML model where inference is performed entirely within the network. A One-sided (AI / ML) model refers to either a UE-side (AI / ML) model or a Network-side (AI / ML) model. A Two-sided (AI / ML) model refers to a pair of AI / ML models where joint inference is performed. Here, joint inference consists of AI / ML inference performed jointly across the UE and the network. That is, the first part of the inference is performed by the UE first, and the remaining part by the gNB, or vice versa.

[0101] AI / ML model transfer refers to the transmission of an AI / ML model via a wireless interface, using parameters of a model structure known to the receiving side or a new model with such parameters. The transmission may include a full model or a partial model. Model download refers to the transmission of a model from the network to the UE. Model upload refers to the transmission of a model from the UE to the network.

[0102] Federated learning / federated training refers to a machine learning technique that trains AI / ML models on multiple distributed edge nodes (e.g., UEs, gNBs), each performing local model training using local data samples. While this requires various interactions between the models, the exchange of local data samples is not necessary. Offline field data is data collected in the field and used for the offline training of AI / ML models. Online field data is data collected in the field and used for the online training of AI / ML models.

[0103] Model monitoring refers to the procedure of monitoring the inference performance of AI / ML models.

[0104] Supervised learning refers to the process of training a model using inputs and their corresponding labels. Unsupervised learning refers to the process of training a model without labeled data. Semi-supervised learning refers to the process of training a model by mixing labeled and unlabeled data. Reinforcement Learning (RL) refers to the process of training an AI / ML model from inputs (i.e., states) and feedback signals (i.e., rewards) resulting from the model's outputs (i.e., actions) in an environment where the model interacts.

[0105] Model activation refers to activating an AI / ML model for a specific function. Model deactivation refers to deactivating an AI / ML model for a specific function. Model switching refers to deactivating the currently activated AI / ML model and activating a different AI / ML model for a specific function.

[0106] When applying AI / ML models, the following levels of network-UE collaboration are considered.

[0107] 1. Level x: No collaboration.

[0108] 2. Level y: Signaling-based collaboration without model migration.

[0109] 3. Level z: Signal-based collaboration via model transmission.

[0110] In relation to life cycle management (LCM) procedures for AI / ML models, the AI / ML model may have a model ID containing relevant information and / or model functions regarding at least some AI / ML operations.

[0111] With regard to model selection, activation, deactivation, switching, and replacement for the UE-side model and both-side models, if determined by the network, the network may initiate the process, or the terminal may initiate and request the network. If determined by the UE, the UE's decision may be reported to the network in accordance with an event configured by the network.

[0112] For AI / ML-based feature groups (FGs), an additional condition refers to all aspects assumed for model training, but it is not part of the UE capability for the AI / ML-based feature group. This does not mean that additional conditions are necessarily explicitly specified. Additional conditions can be divided into two categories: network-side additional conditions and UE-side additional conditions.

[0113] For the inference of the UE-side model, to ensure consistency between training and inference with respect to additional NW-side conditions (if identified), the following options can be taken as possible approaches:

[0114] - Model identification to achieve alignment of additional NW-side conditions between the NW side and the UE side

[0115] - Train the model under additional conditions in the network and deliver it to the UE

[0116] - Provide the UE with information and / or instructions regarding additional conditions on the NW side

[0117] - Consistency is supported by monitoring (model / function selection by UE and / or NW based on the performance of candidate models / functions on the UE side).

[0118] - Other approaches are not excluded

[0119] - The possibility that different approaches can achieve the same function is not denied.

[0120] Regarding data collection, it can be defined as follows.

[0121] For the UE-side AI / ML model on the UE side, the UE reports to the NW a supported / preferred configuration for downlink reference signal (DL RS) transmission. For the data collection trigger / start, data collection may be started / triggered by the NW's configuration or by a request from the UE for data collection.

[0122] Signals / configurations / measurements / reporting for data collection, for example, signaling aspects relate to assistance information (if supported), reference signals, the content / type of collected data, configurations related to Set A and / or Set B, and information regarding the association / mapping between Set A and Set B.

[0123] Support information provided by the network to the UE for the collection of UE data to classify data for the purpose of differentiating data characteristics (where supported). Support information must protect privacy / proprietary information.

[0124] For NW-side AI / ML models, mechanisms related to reporting, additional information regarding report content, reduction of reporting overhead, and signals / configuration / measurement / reporting for data collection, for example, signal aspects are related to supporting information (if supported) and reference signals.

[0125] Regarding data collection for the NW-side AI / ML models of BM-Case1 and BM-Case2, the following approach for overhead reduction is identified:

[0126] - Omission / Selection of collected data

[0127] - Compression of collected data

[0128] - If the purpose of data collection differs, the overhead reduction mechanism and the resulting impact on specifications may differ.

[0129] - For each LCM objective, the support of any mechanisms (if necessary) and potential specification impacts (if any) are subject to separate discussion.

[0130] With regard to data collection for the NW-side AI / ML models of BM-Case1 and BM-Case2, the following reporting signals for beam-specific aspects may apply:

[0131] - L1 signal for reporting collected data

[0132] - Higher-level signals for reporting collected data

[0133] - Does not apply to AI / ML model inference, at least.

[0134] - Existing signaling principles (e.g., L1 RSRP reporting) can be reused.

[0135] RAN1 studies model identification type A, including more details related to use cases.

[0136] RAN1 studies the following options for model identification type B as a starting point, including more details related to all use cases.

[0137] - MI-Option 1: Identify models with data collection-related configurations and / or instructions

[0138] - MI-Option 2: Model identification with dataset transmission

[0139] - MI-Option 3: Model identification in model transfer from NW to UE

[0140] - The names (MI-Option 1, MI-Option 2, MI-Option 3) are used for discussion purposes only.

[0141] - The following other options are suggested for model identification type B:

[0142] - MI-Option 4: Model identification through standardization of reference models (for CSI compression)

[0143] - MI-Option 5: Model identification through model monitoring

[0144] With respect to MI-Option 1 of Model Identification Type B (Model identification with configurations and / or instructions related to data collection), RAN1 further investigates the following aspects:

[0145] - Relationship between Model ID and data collection-related configurations and / or instructions

[0146] - Information transmitted from NW to UE (if any)

[0147] - Information transmitted from UE to NW (if any)

[0148] - Related procedures

[0149] - Usable / Applicable Use Cases of MI-Option 1

[0150] For Model Identification Type B of MI-Option 1 (including data collection configurations and / or instructions related to model identification), RAN1 further investigates the following aspects:

[0151] - Relationship between Model ID and data collection-related configurations and / or instructions

[0152] - Information transmitted from the network (NW) to the UE (if any)

[0153] - Information transmitted from the UE to the network (NW) (if any)

[0154] - Use of MI-Option 1 or applicable use cases

[0155] From the perspective of RAN1, for a UE-side model developed (e.g., trained, updated) on the UE side, the following procedure is an example (AI-Example 1) for further research (including feasibility / necessity) of MI-Option 1.

[0156] - A: For data collection, the NW transmits the data collection-related configuration and its / their associated IDs as a signal.

[0157] Association ID for each sub-use case related to NW-side additional conditions

[0158] - B: The UE collects data corresponding to the associated ID.

[0159] - C: AI / ML models are developed (e.g., trained, updated) on the UE side based on collected data corresponding to the associated ID.

[0160] - D: The UE reports its AI / ML model information corresponding to the associated ID to the NW. A model ID is determined / assigned for each AI / ML model.

[0161] Relationship between Model ID and Associate ID

[0162] Regarding how the model ID is determined / assigned, for example, whether the NW assigns the model ID, the UE assigns / reports the model ID, or an associated ID is considered the model ID, the statement in D “a model ID is determined / assigned for each AI / ML model” is not necessary, and the model ID is determined according to predefined rules.

[0163] D is intended to facilitate AI / ML model inference.

[0164] Additional interaction of steps A / B / C and association IDs between the UE and NW can be considered as an alternative solution for consistency resolution without model identification.

[0165] Regarding association IDs, the UE assumes that NW-side additional conditions with the same association ID are consistent at least within the cell. Whether and how the UE's assumption is applicable to multiple cells (including feasibility studies) is further investigated.

[0166] To ensure consistency of additional NW-side conditions throughout the training and inference of the UE-side model for BM-Case 1 and BM-Case 2, an association ID-based or performance monitoring-based method may be defined.

[0167] The UE may assume that DL Tx beams or beam sets / lists associated with the same Associated ID have similar properties. With respect to the Associated ID, the UE assumes that Network (NW)-side addition conditions with the same Associated ID are consistent within at least one cell.

[0168]

[0169] Currently, 3GPP has agreed to support an associated ID-based approach to ensure that network-side additional conditions applied between inference and training of a UE-sided model remain consistent. An associated ID is associated with a network-side additional condition related to the data used to train an AI / ML model, and if there are datasets for different network-side additional conditions, this implies that they are mapped to different associated IDs. An associated ID associated with a network-side additional condition is defined as consistent within at least one cell and may be applicable to multiple cells. In this disclosure, the term "associated ID" is used by way of example and is not limited to such a term.

[0170] Following discussions regarding Model IDs, an example procedure for associated IDs was agreed upon. According to this procedure, a terminal entering any cell receives the associated ID provided by the cell and related data collection configuration information from the base station, and performs model training / updating by collecting the corresponding data. If the terminal identifies data information for an associated ID for which training has not been performed, the terminal performs data collection for it and can train a new model based on the collected data corresponding to the new associated ID. However, if among the models stored in the terminal's storage, there exists a trained model corresponding to the associated ID for the cell's NW-side additional condition, the terminal can perform communication using that model by sharing this information with the base station.

[0171] According to the discussion so far, the terminal develops (i.e., trains) arbitrary model(s) by collecting data corresponding to arbitrary associated IDs and stores them in its storage. Before the terminal performs communication using a specific model inference, it first checks whether the corresponding network condition(s) are identical to the settings assumed during the model's training. At this time, the presence of additional network-side conditions can be checked using the associated ID corresponding to the trained model (stored in the terminal). In other words, the terminal and the base station will share the associated ID information applicable in the current state in advance of model inference.

[0172] If the associated ID is valid only within a single cell, it means that the model trained by the terminal for that cell is valid only within that same cell, and the model must be retrained every time it enters a new cell. This places a significant burden on the terminal. Furthermore, from the NW's perspective, it can cause significant overhead in data provision because it must continuously provide at least one dataset for newly entering terminals.

[0173] Furthermore, the cell ID used to identify the current cell allows the same cell ID to be reused for different cells during the operation process. If the associated ID were valid only within the cell, a problem would arise where a terminal entering a different cell with the same cell ID would be unable to distinguish the associated ID for a previously trained model. This makes it difficult to guarantee consistency between model training and inference using only the associated ID. In other words, even if a terminal re-enters a cell where the model was trained, it is difficult to determine whether that cell is the one where the model was trained; therefore, it implies that AI / ML model-based communication must be performed through new training every time. If the terminal were to perform model training every time it entered a new cell and reset the model trained in another cell within its storage, it would have to perform the same training every time it entered a cell where training had already been done, leading to a problem of unnecessary repetition of the model training process. To minimize the burden on the UE and NW regarding model training, the associated ID needs to be applied across multiple cells. However, to identify all different associated IDs provided by multiple cells, an associated ID that is too large may be required.

[0174] Furthermore, model training by the terminal may be an action performed optionally by the terminal. If a mobile idle mode terminal can train the model in advance, it has the effect of reducing communication delays that may occur later due to model training.

[0175] As mentioned above, it is necessary to define a method to resolve the overhead issue when associated IDs are applied to multiple cells and to enable idle mode terminals to effectively perform model training.

[0176]

[0177] In the following, a method for performing communication using artificial intelligence and machine learning will be explained in detail with reference to the relevant drawings.

[0178] FIG. 8 is a diagram illustrating a procedure (800) in which a terminal according to one embodiment performs communication using artificial intelligence and machine learning.

[0179] Referring to FIG. 8, the terminal can receive a group ID associated with a dataset provided for training an AI / ML model from a base station (S810).

[0180] As described above, the terminal stores one or more trained AI / ML models corresponding to one or more association IDs. The terminal can train the AI / ML models by collecting data corresponding to at least one association ID for the AI / ML models. When training such AI / ML models, additional network-side conditions indicated by at least one association ID are assumed.

[0181] When a base station indicates information corresponding to additional network-side conditions assumed while training a terminal-side AI / ML model as an associated ID, multiple base stations (or cells) can be grouped according to predetermined conditions, and the associated ID can be recognized based on the grouped groups between the base station and the terminal.

[0182] To this end, according to one example, the group ID may be configured to indicate a group in which base stations containing at least one identical association ID are grouped. That is, base stations with identical network-side additional conditions assumed when providing a dataset for training a terminal-side AI / ML model can be grouped into a single group.

[0183] For example, base stations supporting the same n network-side additional conditions can be grouped into the same group, and one or more association IDs supported by the base stations in that group can be recognized as an arbitrary group ID. Specifically, if Cells 1 and 2 support a dataset corresponding to network-side additional conditions #0 and 1, Cells 1 and 2 identify the dataset corresponding to network-side additional conditions #0 and 1 as association IDs #0 and 1, and set the corresponding group as group ID #0. If Cells 3 and 4 support a dataset corresponding to network-side additional conditions #1, 2, and 3, Cells 3 and 4 identify the dataset corresponding to network-side additional conditions #1, 2, and 3 as association IDs #0, 1, and 2, and set the corresponding group as group ID #1. If cells 5, 6, and 7 support datasets corresponding to network-side additional conditions #4, 5, and 6, cells 5, 6, and 7 separate the datasets corresponding to network-side additional conditions #4, 5, and 6 into association IDs #0, 1, and 2, and set the corresponding group as group ID #2.

[0184] In other words, it can be assumed that the terminal supports a group of the same associated IDs for base stations having the same group ID.

[0185] According to another example, the terminal may be configured to receive, along with the reception of a group ID, at least one additional association ID corresponding to the group ID associated with the data set provided for training the AI / ML model. That is, when base stations are grouped according to certain conditions, the terminal may receive an association ID supported by a base station within the group, along with a group ID indicating the group. That is, the group ID may be configured to indicate a group of base stations to which any association ID is validly applied.

[0186] For example, different network vendors can be mapped into different groups. In this case, a different group ID is assigned to each network vendor, and within each group, network vendors can assign association IDs based on additional network-side conditions.

[0187] Alternatively, for example, geographically adjacent base stations can be mapped into a single group. Even in this case, it can be assumed that identical association IDs within different groups are additional conditions on the other network side.

[0188] Specifically, it is assumed that when base stations 1 and 2 are grouped into a single group designated by group ID #0 according to a predetermined condition, base station 1 identifies a dataset corresponding to network-side additional condition #0,1 as associated ID #0,1, and base station 2 identifies a dataset corresponding to network-side additional condition #2,3 as associated ID #2,3. In this case, in order for a terminal to apply model inference to communication with base station 1, it may receive associated ID #0,1 along with group ID #0.

[0189] According to one example, a group ID associated with a dataset provided for training an AI / ML model may be broadcast from a base station. Additionally, at least one associated ID corresponding to the received group ID may be broadcast or unicast from a base station. Here, broadcasting means that the group ID is transmitted using messages such as SIB, MIB, or Paging that can be received by idle mode terminals. Additionally, unicasting means that the terminal may be received via an RRC configuration message for a terminal that has completed the transition to a connected / inactive state, or via an RRC message used to perform the transition to a connected / inactive state.

[0190] Referring again to FIG. 8, the terminal determines whether the received group ID matches the group ID of the AI / ML model stored in the terminal (S820), and if the received group ID does not match the group ID of the AI / ML model stored in the terminal, it can perform data collection based on at least one associated ID corresponding to the received group ID (S830).

[0191] According to one example, if base stations containing at least one association ID with the same group ID are configured to indicate a grouped group, the terminal can check whether the received group ID matches the group ID corresponding to its trained / stored model. That is, in this case, since the same association ID is configured for base stations within the same group, even if only the group ID matches, the terminal can perform inference using the model corresponding to the group ID among the stored AI / ML models.

[0192] If no matching group ID exists, the terminal can perform data collection corresponding to the group ID. To this end, the terminal requests a dataset provided for training an AI / ML model from a base station, receives configuration information related to data collection corresponding to at least one associated ID, and can collect data based on the configuration information related to data collection.

[0193] According to another example, if the group ID is configured to indicate a group of base stations to which an arbitrary association ID is validly applied under certain conditions, the terminal can check whether the received group ID and the association ID received together match the group ID and association ID corresponding to its trained / stored model. That is, in this case, if the group ID and association ID match, the terminal can perform inference using the model among the stored AI / ML models that corresponds to the group ID.

[0194] If no matching group ID and association ID exist, the terminal may perform data collection corresponding to the received group ID and association ID. To this end, the terminal may request a dataset provided for training an AI / ML model from the base station. In this case, the terminal may transmit the association ID to be applied to the stored AI / ML model together through the request message of the dataset. The terminal receives configuration information related to data collection corresponding to the requested association ID and may collect data based on the configuration information related to data collection.

[0195] The terminal can perform data collection based on configuration information related to data collection received from the base station. In this case, the terminal can receive data for the terminal's data collection based on the configuration information received from the base station.

[0196] The terminal can perform model updates based on collected data. The terminal can store or change internal parameters to OFF, indicating that data collection / transmission for the associated ID of the updated model is required. Additionally, for a trained model, the terminal can store the associated ID corresponding to the dataset and the group ID information of the base station where the training was performed, along with the model.

[0197] According to this, a method and apparatus for performing communication using artificial intelligence and machine learning in a next-generation wireless access network can be provided. In addition, by determining whether model training is required at a base station through the reception of a group ID for the base station, a trained model can be obtained before performing model inference, thereby enabling model inference to be performed in a timely manner as needed. Furthermore, the overall signaling overhead can be reduced by transmitting only the group ID or by signaling only the associated ID within the group ID as needed.

[0198]

[0199] FIG. 9 is a diagram illustrating a procedure (900) in which a base station according to one embodiment performs communication using artificial intelligence and machine learning. The description in FIG. 8 above may be omitted to avoid redundant descriptions, and in this case, the omitted content may be applied substantially the same to the base station as long as it does not contradict the technical concept of the invention.

[0200] Referring to FIG. 9, the base station can transmit a group ID associated with a dataset provided for training an AI / ML model to a terminal (S910).

[0201] When a base station indicates information corresponding to additional network-side conditions assumed during the training of a terminal-side AI / ML model as an associated ID, it may group multiple base stations (or cells) according to predetermined conditions and recognize the associated ID based on the grouped groups between the base station and the terminal.

[0202] To this end, according to one example, the group ID may be configured to indicate a group in which base stations containing at least one identical association ID are grouped. That is, base stations with identical network-side additional conditions assumed when providing a dataset for training a terminal-side AI / ML model can be grouped into a single group.

[0203] For example, base stations supporting the same n network-side additional conditions can be grouped into the same group, and one or more associated IDs supported by the base stations in that group can be recognized as an arbitrary group ID.

[0204] In other words, it can be assumed that the terminal supports a group of the same associated IDs for base stations having the same group ID.

[0205] According to another example, a base station may be configured to transmit at least one association ID corresponding to the group ID associated with the data set provided for training an AI / ML model, along with the transmission of a group ID. That is, when base stations are grouped according to certain conditions, the base station may transmit an association ID supported by a base station within the group, along with a group ID indicating the group. That is, the group ID may be configured to indicate a group of base stations to which any association ID is validly applied.

[0206] For example, different network vendors can be mapped into different groups. In this case, a different group ID is assigned to each network vendor, and within each group, network vendors can assign association IDs based on additional network-side conditions.

[0207] Alternatively, for example, geographically adjacent base stations can be mapped into a single group. Even in this case, it can be assumed that identical association IDs within different groups are additional conditions on the other network side.

[0208] According to one example, a group ID associated with a dataset provided for training an AI / ML model may be broadcast from a base station. Additionally, at least one associated ID corresponding to the received group ID may be broadcast or unicast from a base station. Here, broadcasting means that the group ID is transmitted using messages such as SIB, MIB, or Paging that can be received by idle mode terminals. Additionally, unicasting means that the terminal may be received via an RRC configuration message for a terminal that has completed the transition to a connected / inactive state, or via an RRC message used to perform the transition to a connected / inactive state.

[0209] Referring again to FIG. 9, when a base station receives a request from a terminal for a dataset provided for training an AI / ML model, it transmits data collection configuration information corresponding to at least one associated ID to the terminal (S920), and based on the data collection configuration information, it can transmit data for data collection from the terminal (S930).

[0210] According to one example, if base stations containing at least one association ID with the same group ID are configured to indicate a grouped group, the terminal can check whether the received group ID matches the group ID corresponding to its trained / stored model. That is, in this case, since the same association ID is configured for base stations within the same group, even if only the group ID matches, the terminal can perform inference using the model corresponding to the group ID among the stored AI / ML models.

[0211] If no matching group ID exists, the terminal can perform data collection corresponding to the group ID. To this end, when the base station receives a request from the terminal for a dataset provided for training an AI / ML model, it transmits configuration information related to data collection corresponding to at least one associated ID, and can transmit data to the terminal based on the configuration information related to data collection.

[0212] According to another example, if the group ID is configured to indicate a group of base stations to which an arbitrary association ID is validly applied under certain conditions, the terminal can check whether the received group ID and the association ID received together match the group ID and association ID corresponding to its trained / stored model. That is, in this case, if the group ID and association ID match, the terminal can perform inference using the model among the stored AI / ML models that corresponds to the group ID.

[0213] If no matching group ID and association ID exist, the terminal may perform data collection corresponding to the received group ID and association ID. To this end, the base station may receive an association ID to be applied to a stored AI / ML model, along with a request from the terminal for a dataset provided for training an AI / ML model. The base station may transmit configuration information related to data collection corresponding to the requested association ID and transmit data to the terminal based on the configuration information related to data collection.

[0214] The terminal can perform data collection based on configuration information related to data collection received from the base station. In this case, the base station can transmit data for the terminal's data collection based on the transmitted configuration information.

[0215] The terminal can perform model updates based on collected data. The terminal can store or change internal parameters to OFF, indicating that data collection / transmission for the associated ID of the updated model is required. Additionally, for a trained model, the terminal can store the associated ID corresponding to the dataset and the group ID information of the base station where the training was performed, along with the model.

[0216] According to this, a method and apparatus for performing communication using artificial intelligence and machine learning in a next-generation wireless access network can be provided. In addition, by determining whether model training is required at a base station through the reception of a group ID for the base station, a trained model can be obtained before performing model inference, thereby enabling model inference to be performed in a timely manner as needed. Furthermore, the overall signaling overhead can be reduced by transmitting only the group ID or by signaling only the associated ID within the group ID as needed.

[0217]

[0218] Hereinafter, with reference to the relevant drawings, each embodiment related to a method of performing communication using artificial intelligence and machine learning will be described in detail.

[0219] The present disclosure proposes a method in which, when a network indicates information corresponding to assumed network-side additional condition(s) as an associated ID while training a terminal-side AI / ML model, any associated ID groups valid cells, recognizes the associated ID based on the cell group between the base station and the terminal, and determines whether to train the terminal's model or collect data based on this.

[0220] More specifically, the present disclosure transmits a message to terminal(s) comprising group information (e.g., group ID) to which a base station / cell providing data related to a terminal-side model belongs. Here, base stations / cells belonging to the same group may be defined as follows.

[0221] - Example 1. A set of base stations(s) having the same NW-side additional condition(s) assumed when providing a dataset for training a UE-side AI / ML model.

[0222] For example, base station / cell(s) that support the same n (n is an integer greater than 1) NW-side additional conditions are defined as the same group, and a group of one or more supported associated IDs is recognized as an arbitrary group ID.

[0223] As a more specific example, if cells 1 and 2 support datasets corresponding to NW-side additional conditions #0 and 1, cells 1 and 2 identify the datasets corresponding to NW-side additional conditions #0 and 1 as associated IDs #0 and 1, and set the corresponding group as group ID #0. If cells 3 and 4 support datasets corresponding to NW-side additional conditions #1, 2, and 3, cells 3 and 4 identify the datasets corresponding to NW-side additional conditions #1, 2, and 3 as associated IDs #0, 1, and 2, and set the corresponding group as group ID #1. If cells 5, 6, and 7 support datasets corresponding to NW-side additional conditions #4, 5, and 6, cells 5, 6, and 7 identify the datasets corresponding to NW-side additional conditions #4, 5, and 6 as associated IDs #0, 1, and 2, and set the corresponding group as group ID #2.

[0224] That is, it is assumed that the terminal supports a group of the same associated ID(s) for cells having the same group ID.

[0225] - Example 2. A set of base station(s) to which any associate ID is validly applied.

[0226] For example, associated ID(s) belonging to different NW vendors can be mapped to different groups, and it can be assumed that the same associated ID within different groups represents different NW-side additional conditions. In this case, different group IDs are assigned per NW vendor, and NW vendors assign associated IDs based on NW-side additional conditions according to their implementation.

[0227] And / or, a group of geographically adjacent cell / base station(s) can be mapped as a single group, and it can be assumed that the same associated ID within different groups is a different NW-side additional condition.

[0228]

[0229] The present disclosure proposes broadcasting a group ID associated with a dataset(s) supported by a base station. If, as in Example 1, the group ID signifies that the NW-side additional condition(s) for the cell are identical, the base station may broadcast only the group ID and, if necessary, transmit the associated ID(s) to the terminal via broadcasting / unicasting. If, as in Example 2, the group ID is defined to identify the validity of associated IDs belonging to a specific group, the list of associated ID(s) supported by the base station is broadcast (or unicast) along with the group ID. Here, broadcasting means that the group ID is transmitted using a message (e.g., SIB, MIB, Paging, etc.) that idle mode terminals can receive. Unicasting means that a terminal can receive an RRC configuration message for a terminal that has completed transitioning to a connected / inactive state, or an RRC message used to perform a transition to connected / inactive.

[0230] The idle mode terminal proposed in this disclosure determines whether additional model training or data collection is required through group ID information broadcast from a base station. The idle mode terminal checks the group ID or group ID + associated ID list corresponding to the dataset provided by the cell it has camped on, and if there is no corresponding trained model, it may send a message to the base station requesting a dataset for model training. This may require a state transition of the terminal (Idle -> Connected, or Idle -> Inactive, or Inactive -> Connected).

[0231] Here, the NW-side additional condition(s) corresponding to the associated ID(s) belonging to the group ID transmitted from the base station may be a supported NW-side additional condition supported by the base station / cell, or an applicable NW-side additional condition(s) currently applicable to the base station / cell.

[0232]

[0233] The following describes an example of terminal and base station operation according to the technology of the present disclosure.

[0234] FIG. 10 is a diagram illustrating the operation when base stations with the same associated ID are grouped according to one embodiment.

[0235] First, the case in which Example 1 is applied will be described. Example 1 can be effectively applied in terms of signaling and management by grouping and managing one or more dataset(s) that can be assumed for each cell into a single ID when the NW-side additional condition(s) are similar according to cell characteristics.

[0236] [Terminal Operation]

[0237] - The terminal stores trained model / function(s) corresponding to associated ID(s) belonging to an arbitrary group ID.

[0238] - Receive a message from the base station containing group ID information related to the dataset for model training.

[0239] - The terminal checks if there is an ID that matches the group ID corresponding to its trained / stored model among the received group IDs.

[0240] - If no matching group ID exists, the terminal performs data collection corresponding to the group ID.

[0241] Here, the terminal may transmit to the base station a message instructing the base station to request the dataset(s) or a message including an indicator instructing the base station to request the dataset(s).

[0242] In the case of an Idle / Inactive UE, the message may be an RRC message requesting a state transition to a connected state (e.g., an RRC connection request).

[0243] In the case of a Connected UE, it may be an RRC message for transmitting terminal assistance information or configuration information (e.g., UE Assistance Information (UAI), RRC reconfiguration, etc.), MAC CE, or PHY control signaling.

[0244] - Receive a configuration message related to the above dataset(s) from the base station.

[0245] The above dataset(s) are assigned an associated ID corresponding to each dataset.

[0246] In the case of a dataset for beam management, the above associated ID may be included within the CSI resource / report configuration.

[0247] Based on the received configuration message, the terminal performs data collection and uses the collected data to perform model training.

[0248] Once the training is complete, the model stores the associated ID corresponding to the dataset and the group ID information of the cells that performed the training, along with the model.

[0249] [Base Station Operation]

[0250] - The base station transmits the group ID for the dataset(s) it supports as cell information.

[0251] - The base station may receive a message from the terminal instructing a request for the dataset(s) or a message including an indicator instructing a request for the dataset(s).

[0252] In the case of an Idle / Inactive UE, indicator information directing a request for dataset(s) for training the above model may be included within an RRC message (e.g., an RRC connection request) requesting a state transition to a connected state;

[0253] In the case of a Connected UE, it may be an RRC message for transmitting terminal assistance information or configuration information (e.g., UE Assistance Information (UAI), RRC reconfiguration, etc.), MAC CE, or PHY control signaling.

[0254] - The base station transmits a configuration message related to the above dataset(s) to the terminal.

[0255] The above dataset(s) include an associated ID corresponding to each dataset.

[0256] In the case of a dataset for beam management, the above associated ID may be included within the CSI resource / report configuration.

[0257]

[0258] Next, the case in which Example 2 is applied is described. Example 2 has the effect of reducing overall signaling overhead by dividing and managing groups when the number of associated IDs that the operator must assign / manage is too large.

[0259] FIG. 11 is a diagram for explaining the operation when base stations are grouped according to a predetermined standard according to one embodiment.

[0260] [Terminal Operation]

[0261] - The terminal stores trained model / function(s) corresponding to associated ID(s) belonging to an arbitrary group ID.

[0262] - Receive a message from the base station containing group ID information related to the dataset for model training and a list of associated IDs belonging to it.

[0263] If Base Station 1 belongs to group ID #0 and the associated IDs corresponding to the NW-side additional conditions supported by Base Station 1 are #0, 1, and 2,

[0264] Receiving cell information including Group ID#0-associated IDs #0,1,2

[0265] - The terminal checks if the received group ID + associated ID list contains a function / model that matches a group ID + associated ID corresponding to its trained / stored model.

[0266] - If no matching function / model exists, the terminal performs data collection corresponding to the group ID.

[0267] Here, the terminal may transmit to the base station a message instructing the base station to request the dataset(s) or a message including an indicator instructing the base station to request the dataset(s).

[0268] The message includes the associated ID(s) requested by the terminal.

[0269] In the case of an Idle / Inactive UE, indicator information directing a request for dataset(s) for training the above model may be included within an RRC message (e.g., an RRC connection request) requesting a state transition to a connected state;

[0270] In the case of a Connected UE, it may be an RRC message for transmitting terminal assistance information or configuration information (e.g., UE Assistance Information (UAI), RRC reconfiguration, etc.), MAC CE, or PHY control signaling.

[0271] Receives a configuration message related to the above dataset(s) from the base station.

[0272] The above dataset(s) are assigned an associated ID corresponding to each dataset.

[0273] In the case of a dataset for beam management, the above associated ID may be included within the CSI resource / report configuration.

[0274] Based on the received configuration message, the terminal performs data collection and uses the collected data to perform model training.

[0275] Once the training is complete, the model stores the associated ID corresponding to the dataset and the group ID information of the cells that performed the training, along with the model.

[0276] [Base Station Operation]

[0277] - The base station transmits the group ID and associated ID list for the dataset(s) it supports as cell information.

[0278] - The base station may receive a message from the terminal instructing a request for the dataset(s) or a message including an indicator instructing a request for the dataset(s).

[0279] The message includes the associated ID(s) requested by the terminal.

[0280] In the case of an Idle / Inactive UE, indicator information directing a request for dataset(s) for training the above model may be included within an RRC message (e.g., an RRC connection request) requesting a state transition to a connected state;

[0281] In the case of a Connected UE, it may be an RRC message for transmitting terminal assistance information or configuration information (e.g., UE Assistance Information (UAI), RRC reconfiguration, etc.), MAC CE, or PHY control signaling.

[0282] - The base station transmits a configuration message related to the above dataset(s) to the terminal.

[0283] The above dataset(s) include an associated ID corresponding to each dataset.

[0284] In the case of a dataset for beam management, the above associated ID may be included within the CSI resource / report configuration.

[0285] As described above, the present invention proposes a method for efficiently determining when an idle mode terminal transitions to a state for the purpose of model training by defining an associated ID based on a group ID and transmitting it as cell information. In the case of Option 1, the idle mode terminal can determine whether model training is required at the corresponding base station / cell solely by receiving the group ID for the cell, thereby allowing the terminal to complete model training in advance. This enables model inference to be performed in a timely manner as needed by securing a trained model before actually performing model inference. Furthermore, compared to the case where an associated ID is defined without grouping, it has the effect of reducing overall signaling overhead by transmitting only group information or, if necessary, signaling only the associated ID within the group ID.

[0286]

[0287] According to another embodiment of the present disclosure, the associated ID associated with data collection used to train an AI / ML model of a terminal assumes that the same configuration and network-side additional conditions are applied to one or more cells. This assumes that the same configuration and network-side additional conditions are applied within the same Public Land Mobile Network (PLMN), or that the same information is shared in advance between each base station through pre-defined configuration information within the specification, or through the reception of pre-defined configuration information from a specific server.

[0288] More specifically, the terminal proposed in this disclosure collects data corresponding to any associated ID and, for an AI / ML model trained using the collected data, can perform model inference after verifying performance through model performance monitoring when entering a cell that provides data for the same associated ID. Additionally, if the terminal proposed in this disclosure moves to a cell that does not have settings related to data collection for the same associated ID, it can perform new model training and then perform beam management based on the new model, or operate in a fallback mode (i.e., an NR beam management mode that does not use the AI / ML model). If the associated ID(s) corresponding to the model stored / trained in the terminal are not supported by the target base station but support data corresponding to a new associated ID for the same functionality / feature, the terminal can perform model training by collecting data for the new associated ID, and the model trained in this way can be defined as a new model. If the target base station does not support an associated ID for a trained model and does not support new associated ID-based data corresponding to the same functionality / feature of the trained model, the terminal may operate in a fallback mode that does not use the AI / ML model.

[0289] The present disclosure proposes a method for notifying a terminal of a change in an additional NW-side condition corresponding to an associated ID provided by the NW side, when information corresponding to assumed NW-side conditions is indicated by an associated ID during the training of a terminal-side AI / ML model.

[0290] More specifically, the present disclosure describes a base station providing data for terminal-side model training / inference that transmits a message to terminal(s) containing an indicator indicating version (or update) information corresponding to associated ID(s). Upon receiving this, the terminal further performs data collection corresponding to the received associated ID, thereby performing a model update based on the newly collected data.

[0291] The base station proposed in this disclosure broadcasts system information including associated ID(s) information that it can support and corresponding version / update information. Idle / connected UEs check whether the information corresponding to the associated ID(s) for models in their storage matches the version / update information for the received associated ID. If it is determined that the version information for any associated ID is different or that an update is required, the terminal decides to update the model. When the terminal decides to update the model, the terminal may send a message to the base station requesting data transmission / collection including the associated ID for data collection regarding the determined associated ID. Based on the request message received from the terminal, the base station transmits configuration information for data collection / transmission regarding the associated ID to the terminal, and the terminal is able to perform a model update by performing data collection based on the received configuration information.

[0292] The base station may periodically notify the terminal of information regarding the associated IDs it supports using broadcasting messages, such as system information, but is not limited thereto. If necessary, the base station may transmit messages containing version / update information regarding the base station's associated ID(s) in a terminal-specific manner to terminals supporting AI / ML models.

[0293] When the associated ID(s) proposed in this disclosure and the version / update information therefor are broadcast through system information, they may be transmitted via one of the following messages.

[0294] 1. Transmit via a new SIB-x defined for transmission to AI / ML models; or

[0295] 2. Defined and transmitted within a message of one of the existing SIBs; or

[0296] 3. Transmitted via Paging messages.

[0297] The proposed version information above can be defined with an n-bit size, and the size can be defined in various ways depending on the amount of information, the update frequency, or the scope of application of the associated ID. That is, if only the update status of the associated ID is indicated, the version information can be defined as a 1-bit indication, and if the indication is 1, it indicates that the information for the associated ID has been updated, and if it is 0, it indicates that there is no update.

[0298] Alternatively, the update status can be indicated by checking whether the associated ID is included in the message notifying the update. That is, if the message contains the ID for the associated ID, it indicates that there is an update for that ID; if it does not, it indicates that there is no update for that ID. Alternatively, n-bit version information could be used to notify terminals of the update status, meaning that the version information for the corresponding associated ID changes whenever an update occurs. Upon recognizing that the version has changed, the terminal will update the model by receiving additional data for the associated ID, update the version information of the associated ID for that model, and save it to its storage.

[0299] In addition, if the update status of the associated ID is transmitted as system information, the method of transmitting the update information can be defined as one of the following two methods.

[0300] 1. 1-step indication method

[0301] A. System information includes updated associated ID information and / or configuration information for associated data transmission.

[0302] i. The updated associated ID information can be represented as ID information for the updated associated ID, or it can be indicated by using a bitmap to set only the updated ID to 1.

[0303] ii. The configuration information for data transmission for the updated associated ID is

[0304] 1. Using the above method, data transmission start / end times and window information, and data-related resource information for each associated ID for which an update is instructed may be included.

[0305] 2. 2-step indication method

[0306] A. System information includes only information indicating that there is an update to the associated ID, and the terminal receiving this is configured to receive the updated associated ID and associated data-related configuration information by receiving additional SIB or RRC messages associated therewith.

[0307] B. That is, when an update to an associated ID is indicated using a broadcasting message such as paging, the base station includes a 1-bit indicator within the paging message indicating that there is an update to the associated ID(s). Upon receiving this, the terminal checks specifically which ID has been changed by receiving a related additional message, and if it confirms an update to the associated ID(s) corresponding to the model stored in the terminal, it performs a model update by receiving related data setting information.

[0308] C. Here, the updated associated ID information included in the second message and the configuration information for data transmission associated therewith may be the same as that described in the 1-step indication method above.

[0309] The aforementioned embodiments may be applied independently of each other, or two or more embodiments may be combined and implemented.

[0310]

[0311] Hereinafter, the configuration of a terminal and a base station capable of performing some or all of the embodiments described with reference to FIGS. 1 to 11 will be described with reference to the drawings. The foregoing description may be omitted to avoid redundant descriptions, and in such cases, the omitted content may be applied substantially identically to the following description, provided that it does not contradict the technical concept of the invention.

[0312] FIG. 12 is a diagram showing the configuration of a terminal (1200) according to another embodiment.

[0313] Referring to FIG. 12, a terminal (1200) according to another embodiment includes a transmitting unit (1220), a receiving unit (1230), and a control unit (1210) that controls the transmitting unit and the receiving unit.

[0314] The control unit (1210) controls the overall operation of the terminal (1200) according to the method of performing communication using artificial intelligence and machine learning necessary to perform the above-described embodiments.

[0315] The transmitting unit (1220) and the receiving unit (1230) are used to transmit and receive signals, messages, and data necessary to perform the above-described embodiments with the base station.

[0316] The control unit (1210) may receive a group ID associated with a dataset provided for training an AI / ML model from a base station. As described above, the terminal stores one or more trained AI / ML models corresponding to one or more associated IDs. The control unit (1210) may train an AI / ML model by collecting data corresponding to at least one associated ID for the AI / ML model. When training such an AI / ML model, additional network-side conditions indicated by at least one associated ID are assumed.

[0317] When a base station indicates information corresponding to additional network-side conditions assumed while training a terminal-side AI / ML model as an associated ID, multiple base stations (or cells) can be grouped according to predetermined conditions, and the associated ID can be recognized based on the grouped groups between the base station and the terminal.

[0318] To this end, according to one example, the group ID may be configured to indicate a group in which base stations containing at least one identical association ID are grouped. That is, base stations with identical network-side additional conditions assumed when providing a dataset for training a terminal-side AI / ML model can be grouped into a single group.

[0319] For example, base stations supporting the same n network-side additional conditions can be grouped into the same group, and one or more associated IDs supported by the base stations in that group can be recognized as an arbitrary group ID.

[0320] That is, it can be assumed that the control unit (1210) supports a group of the same associated IDs for base stations having the same group ID.

[0321] According to another example, the control unit (1210) may be configured to receive at least one additional association ID corresponding to the group ID associated with the data set provided for training the AI / ML model, along with the reception of the group ID. That is, when base stations are grouped according to a predetermined condition, the control unit (1210) may receive an association ID supported by a base station within the group, along with a group ID indicating the group. That is, the group ID may be configured to indicate a group of base stations to which any association ID is validly applied.

[0322] For example, different network vendors can be mapped into different groups. In this case, a different group ID is assigned to each network vendor, and within each group, network vendors can assign association IDs based on additional network-side conditions.

[0323] Alternatively, for example, geographically adjacent base stations can be mapped into a single group. Even in this case, it can be assumed that identical association IDs within different groups are additional conditions on the other network side.

[0324] According to one example, a group ID associated with a dataset provided for training an AI / ML model may be broadcast from a base station. Additionally, at least one associated ID corresponding to the received group ID may be broadcast or unicast from a base station. Here, broadcasting means that the group ID is transmitted using messages such as SIB, MIB, or Paging that can be received by idle mode terminals. Additionally, unicasting means that the terminal may be received via an RRC configuration message for a terminal that has completed the transition to a connected / inactive state, or via an RRC message used to perform the transition to a connected / inactive state.

[0325] The control unit (1210) can determine whether the received group ID matches the group ID of the AI / ML model stored in the terminal. If the received group ID does not match the group ID of the AI / ML model stored in the terminal, the control unit (1210) can perform data collection based on at least one associated ID corresponding to the received group ID.

[0326] According to one example, if base stations containing at least one association ID with the same group ID are configured to indicate a grouped group, the control unit (1210) can check whether the received group ID matches the group ID corresponding to its trained / stored model. That is, in this case, since the same association ID is configured for base stations within the same group, even if only the group ID matches, the control unit (1210) can perform inference using the model corresponding to the group ID among the stored AI / ML models.

[0327] If no matching group ID exists, the control unit (1210) can perform data collection corresponding to the group ID. To this end, the control unit (1210) requests a dataset provided for training an AI / ML model from a base station, receives configuration information related to data collection corresponding to at least one associated ID, and can collect data based on the configuration information related to data collection.

[0328] According to another example, if the group ID is configured to indicate a group of base stations to which any associated ID is validly applied according to a predetermined condition, the control unit (1210) can check whether the received group ID and associated ID received together match the group ID and associated ID corresponding to its trained / stored model. That is, in this case, if the group ID and associated ID match, the control unit (1210) can perform inference using the model corresponding to the group ID among the stored AI / ML models.

[0329] If there is no matching group ID and association ID, the control unit (1210) can perform data collection corresponding to the received group ID and association ID. To this end, the control unit (1210) can request a dataset provided for training an AI / ML model from a base station. In this case, the control unit (1210) can transmit the association ID to be applied to the stored AI / ML model together through the request message of the dataset. The control unit (1210) receives configuration information related to data collection corresponding to the requested association ID and can collect data based on the configuration information related to data collection.

[0330] The control unit (1210) can perform data collection based on configuration information related to data collection received from the base station. In this case, the control unit (1210) can receive data for data collection of the terminal based on the configuration information received from the base station.

[0331] The control unit (1210) can perform a model update based on collected data. The control unit (1210) can store / change internal terminal parameters to OFF, indicating that data collection / transmission for the associated ID for the updated model is required. Additionally, the control unit (1210) can store the associated ID corresponding to the dataset and the group ID information of the base station that performed the training, along with the model, for the model that has completed training.

[0332] According to this, a method and apparatus for performing communication using artificial intelligence and machine learning in a next-generation wireless access network can be provided. In addition, by determining whether model training is required at a base station through the reception of a group ID for the base station, a trained model can be obtained before performing model inference, thereby enabling model inference to be performed in a timely manner as needed. Furthermore, the overall signaling overhead can be reduced by transmitting only the group ID or by signaling only the associated ID within the group ID as needed.

[0333] FIG. 13 is a diagram showing the configuration of a base station (1300) according to another embodiment.

[0334] Referring to FIG. 13, a base station (1300) according to another embodiment includes a transmitter (1320), a receiver (1330), and a control unit (1310) that controls the transmitter and the receiver.

[0335] The control unit (1310) controls the overall operation of the base station (1300) and the operation of the repeater according to the method of performing communication using artificial intelligence and machine learning necessary to perform the above-described embodiments.

[0336] The transmitting unit (1320) and the receiving unit (1330) are used to transmit and receive signals, messages, and data to and from the terminal that are necessary to perform the above-described embodiments.

[0337] The control unit (1310) can transmit a group ID associated with a dataset provided for training an AI / ML model to a terminal. When the control unit (1310) directs information corresponding to additional network-side conditions assumed during the training of the terminal-side AI / ML model as an associated ID, it can group multiple base stations (or cells) according to a predetermined condition and recognize the associated ID based on the grouped group between the base station and the terminal.

[0338] To this end, according to one example, the group ID may be configured to indicate a group in which base stations containing at least one identical association ID are grouped. That is, base stations with identical network-side additional conditions assumed when providing a dataset for training a terminal-side AI / ML model can be grouped into a single group.

[0339] For example, base stations supporting the same n network-side additional conditions can be grouped into the same group, and one or more associated IDs supported by the base stations in that group can be recognized as an arbitrary group ID.

[0340] In other words, it can be assumed that the terminal supports a group of the same associated IDs for base stations having the same group ID.

[0341] According to another example, the control unit (1310) may be configured to transmit at least one association ID corresponding to the group ID associated with the data set provided for training the AI / ML model, along with the transmission of the group ID. That is, when base stations are grouped according to a predetermined condition, the control unit (1310) may transmit the association ID supported by the base station within the group, along with the group ID indicating the group. That is, the group ID may be configured to indicate a group of base stations to which any association ID is validly applied.

[0342] For example, different network vendors can be mapped into different groups. In this case, a different group ID is assigned to each network vendor, and within each group, network vendors can assign association IDs based on additional network-side conditions.

[0343] Alternatively, for example, geographically adjacent base stations can be mapped into a single group. Even in this case, it can be assumed that identical association IDs within different groups are additional conditions on the other network side.

[0344] According to one example, a group ID associated with a dataset provided for training an AI / ML model may be broadcast from a base station. Additionally, at least one associated ID corresponding to the received group ID may be broadcast or unicast from a base station. Here, broadcasting means that the group ID is transmitted using messages such as SIB, MIB, or Paging that can be received by idle mode terminals. Additionally, unicasting means that the terminal may be received via an RRC configuration message for a terminal that has completed the transition to a connected / inactive state, or via an RRC message used to perform the transition to a connected / inactive state.

[0345] When the control unit (1310) receives a request from the terminal for a dataset provided for training an AI / ML model, it can transmit data collection configuration information corresponding to at least one associated ID to the terminal. Based on the data collection configuration information, the control unit (1310) can transmit data for data collection by the terminal.

[0346] According to one example, if base stations containing at least one association ID with the same group ID are configured to indicate a grouped group, the terminal can check whether the received group ID matches the group ID corresponding to its trained / stored model. That is, in this case, since the same association ID is configured for base stations within the same group, even if only the group ID matches, the terminal can perform inference using the model corresponding to the group ID among the stored AI / ML models.

[0347] If no matching group ID exists, the terminal can perform data collection corresponding to the group ID. To this end, when the control unit (1310) receives a request from the terminal for a dataset provided for training an AI / ML model, it can transmit configuration information related to data collection corresponding to at least one associated ID and transmit data to the terminal based on the configuration information related to data collection.

[0348] According to another example, if the group ID is configured to indicate a group of base stations to which an arbitrary association ID is validly applied under certain conditions, the terminal can check whether the received group ID and the association ID received together match the group ID and association ID corresponding to its trained / stored model. That is, in this case, if the group ID and association ID match, the terminal can perform inference using the model among the stored AI / ML models that corresponds to the group ID.

[0349] If there are no matching group IDs and association IDs, the terminal can perform data collection corresponding to the received group IDs and association IDs. To this end, the control unit (1310) can receive an association ID to be applied to a stored AI / ML model along with a request from the terminal for a dataset provided for training an AI / ML model. The control unit (1310) can transmit configuration information related to data collection corresponding to the requested association ID and transmit data to the terminal based on the configuration information related to data collection.

[0350] The terminal can perform data collection based on configuration information related to data collection received from the base station. In this case, the control unit (1310) can transmit data for data collection by the terminal based on the transmitted configuration information.

[0351] The terminal can perform model updates based on collected data. The terminal can store or change internal parameters to OFF, indicating that data collection / transmission for the associated ID of the updated model is required. Additionally, for a trained model, the terminal can store the associated ID corresponding to the dataset and the group ID information of the base station where the training was performed, along with the model.

[0352] According to this, a method and apparatus for performing communication using artificial intelligence and machine learning in a next-generation wireless access network can be provided. In addition, by determining whether model training is required at a base station through the reception of a group ID for the base station, a trained model can be obtained before performing model inference, thereby enabling model inference to be performed in a timely manner as needed. Furthermore, the overall signaling overhead can be reduced by transmitting only the group ID or by signaling only the associated ID within the group ID as needed.

[0353] The above-described embodiments may be supported by standard documents disclosed in at least one of the wireless access systems IEEE 802, 3GPP, and 3GPP2. That is, steps, configurations, and parts in the embodiments that are not described to clearly reveal the technical concept may be supported by the aforementioned standard documents. Furthermore, all terms disclosed in this specification may be explained by the standard documents disclosed above.

[0354] The embodiments described above may be implemented through various means. For example, the embodiments may be implemented by hardware, firmware, software, or a combination thereof.

[0355] In the case of implementation by hardware, the method according to the embodiments may be implemented by one or more ASICs (Application Specific Integrated Circuits), DSPs (Digital Signal Processors), DSPDs (Digital Signal Processing Devices), PLDs (Programmable Logic Devices), FPGAs (Field Programmable Gate Arrays), processors, controllers, microcontrollers, or microprocessors.

[0356] In the case of implementation by firmware or software, the method according to the embodiments may be implemented in the form of a device, procedure, or function that performs the functions or operations described above. Software code may be stored in a memory unit and executed by a processor. The memory unit may be located inside or outside the processor and may exchange data with the processor by various means already known.

[0357] Additionally, terms such as "system," "processor," "controller," "component," "module," "interface," "model," or "unit" described above may generally refer to computer-related entities, hardware, combinations of hardware and software, software, or running software. For example, the aforementioned components may be, but are not limited to, processes driven by a processor, processors, controllers, control processors, objects, execution threads, programs, and / or computers. For example, both the application running on the controller or processor and the controller or processor may be components. One or more components may reside within a process and / or execution thread, and the components may be located on a single device (e.g., a system, a computing device, etc.) or distributed across two or more devices.

[0358] The foregoing description is merely an illustrative explanation of the technical concept of the present disclosure, and those skilled in the art to which the present disclosure pertains may make various modifications and variations within the scope of the essential characteristics of the technical concept. Furthermore, since these embodiments are intended to explain, not limit, the scope of the technical concept is not limited by these embodiments. The scope of protection of the present disclosure shall be interpreted by the claims below, and all technical concepts within an equivalent scope shall be interpreted as being included within the scope of rights of the present disclosure.

[0359]

[0360] CROSS-REFERENCE TO RELATED APPLICATION

[0361] This patent application claims priority pursuant to Section 119(a) of the U.S. Patent Act (35 USC § 119(a)) to Patent Application No. 10-2024-0124972 filed in Korea on September 12, 2024 and Patent Application No. 10-2025-0130259 filed in Korea on September 11, 2025, all of which are incorporated by reference into this patent application. Furthermore, this patent application claims priority in countries other than the United States for the same reasons as above, all of which are incorporated by reference into this patent application.

Claims

1. A method in which a terminal (user equipment; UE) performs communication using artificial intelligence and machine learning (AI / ML), A step of receiving a group ID associated with a dataset provided for training an AI / ML model from a base station; A step of determining whether the received group ID matches the group ID for the AI / ML model stored in the terminal; and A method comprising the step of performing data collection based on at least one associated ID corresponding to the received group ID when the received group ID and the group ID for the AI / ML model stored in the terminal do not match.

2. In Paragraph 1, The above group ID is, A method configured such that base stations containing at least one identical associated ID are configured to indicate a grouped group.

3. In Paragraph 1, The step of receiving the above group ID is, A method for receiving at least one additional association ID corresponding to a group ID associated with a dataset provided for training the above AI / ML model.

4. In Paragraph 1, The group ID associated with the dataset provided for training the above AI / ML model is, Broadcasted from the above base station, At least one association ID corresponding to the received group ID is, A method of broadcasting or unicasting from the above base station.

5. In Paragraph 1, The step of performing the above data collection is, A method for requesting a dataset provided for training the AI / ML model from the base station, receiving data collection configuration information corresponding to at least one associated ID, and collecting data based on the data collection configuration information.

6. A method for a base station to perform communication using artificial intelligence and machine learning (AI / ML), A step of transmitting a group ID associated with a dataset provided for training an AI / ML model to a terminal; When a request for a dataset provided for training the AI / ML model is received from the terminal, the step of transmitting data collection configuration information corresponding to at least one associated ID to the terminal; and A method comprising the step of transmitting data for data collection of the terminal based on the above data collection configuration information.

7. In Paragraph 6, The above group ID is, A method configured such that base stations containing at least one identical associated ID are configured to indicate a grouped group.

8. In Paragraph 6, The step of transmitting the above group ID is, A method for transmitting at least one additional association ID corresponding to a group ID associated with a dataset provided for training the above AI / ML model.

9. In Paragraph 6, The group ID associated with the dataset provided for training the above AI / ML model is, Broadcast to the above terminal, At least one association ID corresponding to a group ID associated with a dataset provided for training the above AI / ML model is, A method of broadcasting or unicasting to the above terminal.

10. In a terminal (user equipment; UE) that performs communication using artificial intelligence and machine learning (AI / ML), Transmitter; Receiver; and It includes a control unit that controls the operation of the transmitting unit and the receiving unit, wherein The above control unit is, A terminal that receives a group ID associated with a dataset provided for training an AI / ML model from a base station, determines whether the received group ID matches a group ID for an AI / ML model stored in the terminal, and if the received group ID does not match a group ID for an AI / ML model stored in the terminal, performs data collection based on at least one associated ID corresponding to the received group ID.

11. In Paragraph 10, The above group ID is, A terminal configured to indicate a group of base stations including at least one identical association ID.

12. In Paragraph 10, The above control unit is, A terminal that receives at least one additional association ID corresponding to a group ID associated with a dataset provided for training the above AI / ML model.

13. In Paragraph 10, The group ID associated with the dataset provided for training the above AI / ML model is, Broadcasted from the above base station, At least one association ID corresponding to the received group ID is, A terminal that is broadcast or unicast from the above base station.

14. In Paragraph 10, The above control unit is, A terminal that requests a dataset provided for training the AI / ML model from the base station, receives data collection configuration information corresponding to at least one associated ID, and collects data based on the data collection configuration information.

Images